© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 19845
    Prev
    Next
    INDEX
    Explanations

    instances where someone owes something to someone else

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial obligations or debts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cross
    -0.79
     EVENTS
    -0.66
     Chocobo
    -0.65
    aque
    -0.65
     Machina
    -0.63
    design
    -0.63
    dar
    -0.63
     Inferno
    -0.62
    unch
    -0.62
    ãĥİ
    -0.61
    POSITIVE LOGITS
     owed
    1.09
     owe
    0.88
     repayment
    0.87
     owes
    0.86
     forgiven
    0.84
    Credit
    0.80
    owship
    0.80
     dues
    0.76
     dishon
    0.76
     repay
    0.75
    Activations Density 0.010%

    No Known Activations